depix-mcp
MCP server for DePix App that enables AI agents to receive Pix payments and read transaction status via the DePix API.
README
depix-mcp
MCP (Model Context Protocol) server for DePix App — the agent-facing interface of the non-custodial Pix↔DePix payment gateway.
Connect an AI agent (Claude Code, Claude Desktop, Cursor, or any MCP client) and
it can receive Pix payments (checkouts and products) and read transaction
status — end to end, in sandbox (sk_test_) and production (sk_live_).
- Remote (Streamable HTTP):
https://mcp.depixapp.com/mcp - Local (stdio):
npx -y @depixapp/mcpwithDEPIX_API_KEYin the environment
What it is (and isn't)
- A pure client of the public DePix API (
https://api.depixapp.com/api/*). It holds zero critical credentials — no Eulen token, no database, no webhook HMAC, no Liquid key. - Never custodial. It never signs a transaction, never holds funds, never
stores your key. Your
sk_key is passed verbatim to the API on each call and lives only in memory for that request. - Same door as everyone. The MCP goes through the same auth, scopes and rate limits as any external agent — no privileged path.
It does not create deposits or withdrawals (that moves funds and belongs to the Wallet SDK). The pay-side tools here are read-only status reads.
Quickstart 1 — Connect Claude Code (remote, HTTP)
Pass your DePix API key as a Bearer header. Always start with a sandbox key.
claude mcp add --transport http depix https://mcp.depixapp.com/mcp \
--header "Authorization: Bearer sk_test_YOUR_KEY"
Then test the connection by asking Claude to run get_account. It should return
your merchant with is_live: false (sandbox).
Cursor — add to ~/.cursor/mcp.json (or a project .cursor/mcp.json):
{
"mcpServers": {
"depix": {
"url": "https://mcp.depixapp.com/mcp",
"headers": { "Authorization": "Bearer sk_test_YOUR_KEY" }
}
}
}
Or use the one-click deeplink. The key placeholder lives INSIDE the base64
config= value, so re-encode it with your real key first:
node -e 'const cfg={url:"https://mcp.depixapp.com/mcp",headers:{Authorization:"Bearer sk_test_YOUR_KEY"}};console.log(Buffer.from(JSON.stringify(cfg)).toString("base64"))'
cursor://anysphere.cursor-deeplink/mcp/install?name=depix&config=<base64 from the command above>
The claude.ai web UI custom-connector only supports OAuth (no custom header), so the web UI cannot connect in this MVP. Claude Desktop is covered by the local stdio mode below; the OAuth shim is planned for a later phase.
Quickstart 2 — Local stdio (Claude Desktop)
The same server runs as a local process over stdio. The key comes from
DEPIX_API_KEY (env), never a flag. The only official npm package is
@depixapp/mcp — the @depixapp scope is organization-owned; do not install
any similarly-named unscoped package. Add to your Claude Desktop config
(claude_desktop_config.json):
{
"mcpServers": {
"depix": {
"command": "npx",
"args": ["-y", "@depixapp/mcp"],
"env": { "DEPIX_API_KEY": "sk_test_YOUR_KEY" }
}
}
}
Run it directly to sanity-check:
DEPIX_API_KEY=sk_test_YOUR_KEY npx -y @depixapp/mcp
Quickstart 3 — Sandbox testing (the full loop)
Always test with an sk_test_ key before sk_live_. Sandbox QRs are
non-payable placeholders (SANDBOX-…-DO-NOT-PAY).
-
create_checkout—amountandpayer_tax_numberare both required (the CPF/CNPJ is required even in sandbox). Use a test CPF like52998224725:{ "amount": 1500, "payer_tax_number": "52998224725" }Returns a
chk_…id, apayment_url, a sandboxpix.qr_code, andis_live: false. -
simulate_checkout_payment—{ "checkout_id": "chk_…" }marks the sandbox checkout paid (sandbox-only; live checkouts returnsandbox_only). -
wait_for_checkout—{ "checkout_id": "chk_…" }. The server polls internally and streams progress; you make one call and it returns{ "status": "completed", "terminal": true }— no client-side polling loop.
You can also read a synthetic deposit: get_deposit_status with a
sandbox_… id returns depix_sent.
Tools (16)
| Tool | API | Scope |
|---|---|---|
create_checkout |
POST /api/checkouts | merchant_write |
get_checkout |
GET /api/checkouts/:id | merchant_read |
list_checkouts |
GET /api/checkouts | merchant_read |
simulate_checkout_payment |
POST /api/checkouts/:id/simulate-payment | merchant_write (sandbox-only) |
wait_for_checkout |
GET /api/checkouts/:id (server-side loop) | merchant_read |
create_product |
POST /api/products | merchant_write |
list_products |
GET /api/products | merchant_read |
get_product |
GET /api/products/:id | merchant_read |
update_product |
PATCH /api/products/:id | merchant_write |
activate_product |
POST /api/products/:id/activate | merchant_write |
deactivate_product |
POST /api/products/:id/deactivate | merchant_write |
set_featured_products |
POST /api/products/featured | merchant_write |
list_product_checkouts |
GET /api/products/:id/checkouts | merchant_read |
get_account |
GET /api/me | merchant_read |
get_deposit_status |
GET /api/deposits/:id | wallet_read (read-only) |
get_withdrawal_status |
GET /api/withdrawals/:id | wallet_read (read-only) |
Amounts are BRL cents. A tool call whose key lacks the required scope returns an
insufficient_scope tool error naming the missing scope — that is the only way
to discover a missing scope (the API never lists a key's scopes).
Configuration (public, no secrets)
| Env | Meaning | Default |
|---|---|---|
DEPIX_API_BASE |
API base URL (allowlisted origins only) | https://api.depixapp.com |
MCP_MAX_WAIT_SECONDS |
Max wait_for_checkout budget; prod sets ~780 (Vercel Pro) |
290 (Hobby-safe) |
MCP_SERVER_VERSION |
Version reported in the handshake | 1.0.0 |
MCP_ALLOWED_HOSTS |
Comma-separated Host allowlist (DNS-rebinding protection); set on previews to add the *.vercel.app host |
mcp.depixapp.com |
DEPIX_API_KEY |
stdio mode only — your sk_ key |
— |
There is deliberately no env for an API key, Eulen token, HMAC or DB
credential in the remote server. In HTTP mode the key arrives per-request in the
Authorization header.
Endpoints
POST /mcp— the MCP Streamable HTTP endpoint (DELETEends a session;GETreturns 405 — this stateless server offers no standalone SSE stream).GET /.well-known/mcp.json— minimal discovery document.GET /api/health(also/) — service status.
Development
npm install
npm test # vitest
npm run typecheck # tsc --noEmit
npm run lint # eslint
npm run build # compile src → dist (the stdio bin)
Set DEPIX_TEST_KEY=sk_test_… to run the real-sandbox e2e test
(test/e2e/sandbox.test.ts), otherwise it is skipped.
Release smoke test
After a preview/production deploy:
claude mcp add --transport http depix <url>/mcp --header "Authorization: Bearer sk_test_…"- Ask Claude to run
get_account→ returns the merchant,is_live: false. create_checkout(sandbox) →simulate_checkout_payment→wait_for_checkout→completed.
Pushing to
maindeploys to production (mcp.depixapp.com). Validate on a Vercel preview deploy before merging. Preview hosts are not on the default DNS-rebinding allowlist — setMCP_ALLOWED_HOSTSin the preview environment (e.g.mcp.depixapp.com,depix-mcp-<hash>.vercel.app) to smoke-test there.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。